Run 4. Outer Step 5. Inner Step 1.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5487870,
-    5487873,
-    5487875,
-    5487878,
-    5487880,
-    5487882,
-    5487883,
-    5487884
+    5487886,
+    5487888,
+    5487890,
+    5487893,
+    5487896
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 1,
   "inner_steps": 0,
   "last_allreduce_block": 5487765,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb9541d16728feb114901179b2e70c85b76d0cc992998549b977736498995621
+oid sha256:72c4fb72e69afcac01e3fdf53d0356750e23e4abceffe71da6274e529f8df669
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75efff6244c91f472ca7488b0cf4d7916669f33896c4e5c97ec2e2c41bde1126
+oid sha256:2775c0e1c9edc25e60eef00590c407261b08011e8ea9edb193fb4ffa714fa88a
 size 4040701744